workflow-big-feature

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow's required " /web-research " step (in the "Steps:" list) indicates the agent will fetch/ingest public web content as part of its runtime research flow, so untrusted third‑party material could be read and influence subsequent decisions/actions.